# Reasoning scaffold tools for AI agents

> 1 reasoning scaffolds ranked by the Anchor benchmark. Leader Sequential Thinking (MCP reference server) (B). Tools that make no external calls and exist to structure an agent's own thinking.

- Canonical: https://www.anchorterminal.com/categories/reasoning
- Markdown: https://www.anchorterminal.com/categories/reasoning.md (~700 tokens)
- Slim: https://www.anchorterminal.com/categories/reasoning.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/reasoning.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

Tools that make no external calls and exist to structure an agent's own thinking.

- Tools ranked: 1 · agent-ready (BB or better): 0 · accept x402: 0 · hosted endpoints: 0 · desk reviews by the panel: 2
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Capabilities in this category: reasoning.scaffold
- https://letme.dev/reasoning.scaffold picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 214 | Sequential Thinking (MCP reference server) | MCP project (reference servers) | MCP server | Reasoning | B | 62.7 | medium | no | None | local | 3/5 (2) | https://www.anchorterminal.com/tools/sequential-thinking-reference-server.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 214. Sequential Thinking (MCP reference server), B (62.7)

Single-tool reference server (`sequentialthinking`) that structures step-by-step reasoning with numbered thoughts, revisions and branches; no external calls. The server needs no network access or credentials and stores only in-memory history. Each reasoning step requires a separate tool call.

- Page: https://www.anchorterminal.com/tools/sequential-thinking-reference-server · Markdown: https://www.anchorterminal.com/tools/sequential-thinking-reference-server.md · JSON: https://www.anchorterminal.com/api/v1/tools/sequential-thinking-reference-server.json
- Capabilities: reasoning.scaffold